Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    read

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Az
    -0.07
     يج
    -0.07
     sacrifices
    -0.06
    ��
    -0.06
     einen
    -0.06
    喔
    -0.06
    orgeous
    -0.06
     Plaza
    -0.06
     prostituerte
    -0.06
    /Gate
    -0.06
    POSITIVE LOGITS
     ws
    0.07
     recover
    0.06
     caption
    0.06
     REGISTER
    0.06
     legis
    0.06
    Expose
    0.06
    workers
    0.06
     usernames
    0.06
     ourselves
    0.06
    _billing
    0.06
    Act Density 0.001%

    No Known Activations